search

HannesStark / EquiBind

EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein
MIT License
477 stars 109 forks source link

Blind Docking - Using the whole protein or only just part of protein #66

Closed lkqnaruto closed 4 months ago

lkqnaruto commented 1 year ago

Hi Hannes,

I wonder when you consider blind docking scenario, did you use the whole problem to build the graph or just a part of protein, like a neighborhood around the binding pocket?

Btw, great work! Thanks

HannesStark commented 4 months ago

We used the whole protein.

Sorry for the late reply.